license, datasets, language, metrics, library_name, tags, pipeline_tag, widget, inference, co2_eq_emissions, base_model

license	datasets	language	metrics	library_name	tags	pipeline_tag	widget	inference	co2_eq_emissions	base_model
bigscience-bloom-rail-1.0	nicholasKluge/instruct-aira-dataset	pt	accuracy	transformers	alignment instruction tuned text generation conversation assistant	text-generation	text example_title <|startofinstruction|>Me explique o que é Aprendizagem de Máquina?<|endofinstruction|> Aprendizagem de Máquina text example_title <|startofinstruction|>Você sabe alguma coisa sobre a Ética das Virtudes?<|endofinstruction|> Ética text example_title <|startofinstruction|>Como eu posso fazer a minha namorada feliz?<|endofinstruction|> Conselho	parameters repetition_penalty temperature top_k top_p max_new_tokens early_stopping 1.2 0.1 50 1.0 200 true	emissions source training_type geographical_location hardware_used 1990 CodeCarbon fine-tuning Singapore NVIDIA A100-SXM4-40GB	bigscience/bloom-1b7

Aira-2-portuguese-1B7

Aira-2 is the second version of the Aira instruction-tuned series. Aira-2-portuguese-1B7 is an instruction-tuned model based on BLOOM. The model was trained with a dataset composed of prompts and completions generated synthetically by prompting already-tuned models (ChatGPT, Llama, Open-Assistant, etc).

Check our gradio-demo in Spaces.

Details

• Size: 1,722,005,504 parameters
• Dataset: Instruct-Aira Dataset
• Language: Portuguese
• Number of Epochs: 3
• Batch size: 4
• Optimizer: torch.optim.AdamW (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
• GPU: 1 NVIDIA A100-SXM4-40GB
• Emissions: 1.99 KgCO2 (Singapore)
• Total Energy Consumption: 4.09 kWh

This repository has the source code used to train this model.

Usage

Three special tokens are used to mark the user side of the interaction and the model's response:

<|startofinstruction|>O que é um modelo de linguagem?<|endofinstruction|>Um modelo de linguagem é uma distribuição de probabilidade sobre um vocabulário.<|endofcompletion|>

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = torch.device("cuda"  if torch.cuda.is_available() else  "cpu")

tokenizer = AutoTokenizer.from_pretrained('nicholasKluge/Aira-2-portuguese-1B7')
aira = AutoModelForCausalLM.from_pretrained('nicholasKluge/Aira-2-portuguese-1B7')

aira.eval()
aira.to(device)

question =  input("Enter your question: ")

inputs = tokenizer(tokenizer.bos_token + question + tokenizer.sep_token,
  add_special_tokens=False,
  return_tensors="pt").to(device)

responses = aira.generate(**inputs,
	do_sample=True,
	top_k=50,
	top_p=0.95,
	temperature=0.7,
	num_return_sequences=2)

print(f"Question: 👤 {question}\n")

for i, response in  enumerate(responses):
	print(f'Response {i+1}: 🤖 {tokenizer.decode(response, skip_special_tokens=True).replace(question, "")}')

The model will output something like:

>>> Question: 👤 Qual a capital da Alemanha?

>>>Response 1: 🤖 A capital da Alemanha é Berlim. É a maior cidade da Alemanha e serve como centro administrativo, cultural e político da Alemanha.
>>>Response 2: 🤖 A capital da Alemanha é Berlim. É a maior cidade da Alemanha e serve como centro administrativo, cultural e político da Alemanha.

Limitations

• Hallucinations: This model can produce content that can be mistaken for truth but is, in fact, misleading or entirely false, i.e., hallucination.

• Biases and Toxicity: This model inherits the social and historical stereotypes from the data used to train it. Given these biases, the model can produce toxic content, i.e., harmful, offensive, or detrimental to individuals, groups, or communities.

• Repetition and Verbosity: The model may get stuck on repetition loops (especially if the repetition penalty during generations is set to a meager value) or produce verbose responses unrelated to the prompt it was given.

Cite as 🤗

@misc{nicholas22aira,
  doi = {10.5281/zenodo.6989727},
  url = {https://github.com/Nkluge-correa/Aira},
  author = {Nicholas Kluge Corrêa},
  title = {Aira},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
}

@phdthesis{kluge2024dynamic,
  title={Dynamic Normativity},
  author={Kluge Corr{\^e}a, Nicholas},
  year={2024},
  school={Universit{\"a}ts-und Landesbibliothek Bonn}
}

License

Aira-2-portuguese-1B7 is licensed under the RAIL License since it is a model derived from BLOOM. See the LICENSE file for more details.